Segmentation and Recognition of Arabic Printed Script

In this work we present a method for the recognition of Arabic printed script. The major problem of the automatic reading of cursive writing is a segmentation of script to isolate characters. The recognition process consists of four phases: Preprocessing, segmentation, feature extraction and the recognition. In the preprocessing, the image is scanned and smoothed. The correction of skew lines is done by using Hough transform . In the second phase, the text is segmented into lines, words or parts of words and each word into characters based on the principle of projection of the histogram. Features such as: density, profile, Hu moments and histogram are used to classifier the characters based on the Neural network.